Titre :	Classification and Forecasting using Deep Learning Approach for Time Series Gene Expression Data
Type de document :	texte imprimé
Auteurs :	Abderraouf Aymen Bensemra, Auteur ; Assil Guenfoud, Auteur ; Nasri,Khaled, Directeur de thèse
Année de publication :	2023
Importance :	1 vol (40 f .)
Format :	29cm
Langues :	Français (fre)
Catégories :	Thèses & Mémoires:Informatique
Mots-clés :	Informatique
Index. décimale :	004 Informatique
Résumé :	Time series gene expression analysis reveals dynamic shifts in gene expression patterns over time, aiding the study of regulatory genes, signaling pathways, and biological processes. It provides insights into development, environmental responses, and disease progression, deepening our understanding and enabling specialized interventions. Deep learning algorithms for gene expression time series forecasting offer significant benefits, accurately predicting future expression levels by capturing temporal dependencies and non-linear correlations. They enhance precision medicine and our understanding of biological processes. In our study, in the data GSE6168 we evaluated the effectiveness of Long Short-Term Memory where the best RMSE we got is:0.278 and Temporal Convolutional Networks where we got a total RMSE of:0.268
Côte titre :	MAI/0704
En ligne :	https://drive.google.com/file/d/15WXNGAo0lEgxoqlRMtyRXTe49Nu7xX_u/view?usp=drive [...]
Format de la ressource électronique :	pdf

Classification and Forecasting using Deep Learning Approach for Time Series Gene Expression Data [texte imprimé] / Abderraouf Aymen Bensemra, Auteur ; Assil Guenfoud, Auteur ; Nasri,Khaled, Directeur de thèse . - 2023 . - 1 vol (40 f .) ; 29cm.
Langues : Français (fre)

Catégories :	Thèses & Mémoires:Informatique
Mots-clés :	Informatique
Index. décimale :	004 Informatique
Résumé :	Time series gene expression analysis reveals dynamic shifts in gene expression patterns over time, aiding the study of regulatory genes, signaling pathways, and biological processes. It provides insights into development, environmental responses, and disease progression, deepening our understanding and enabling specialized interventions. Deep learning algorithms for gene expression time series forecasting offer significant benefits, accurately predicting future expression levels by capturing temporal dependencies and non-linear correlations. They enhance precision medicine and our understanding of biological processes. In our study, in the data GSE6168 we evaluated the effectiveness of Long Short-Term Memory where the best RMSE we got is:0.278 and Temporal Convolutional Networks where we got a total RMSE of:0.268
Côte titre :	MAI/0704
En ligne :	https://drive.google.com/file/d/15WXNGAo0lEgxoqlRMtyRXTe49Nu7xX_u/view?usp=drive [...]
Format de la ressource électronique :	pdf